%A R.F. Ahmad
%A A.S. Malik
%A N. Kamel
%A F. Reza
%I Institute of Electrical and Electronics Engineers Inc.
%T Machine learning approach for classifying the cognitive states of the human brain with functional magnetic resonance imaging (fMRI)
%R 10.1109/ICIAS.2016.7824133
%D 2017
%L scholars8990
%J International Conference on Intelligent and Advanced Systems, ICIAS 2016
%O cited By 1; Conference of 6th International Conference on Intelligent and Advanced Systems, ICIAS 2016 ; Conference Date: 15 August 2016 Through 17 August 2016; Conference Code:125970
%K Artificial intelligence; Brain; Learning systems; Magnetic resonance imaging; Neuroimaging, Activated regions; Cognitive loads; Cognitive state; Functional magnetic resonance imaging; Functional MRI; Machine learning approaches; Regions of interest; Spatial resolution, Functional neuroimaging
%X Cognitive state classification is a challenging task. Many studies were reported using different neuroimaging modalities for classification of the cognitive states of the human brain e.g., EEG, fMRI, MEG etc. However, functional MRI seems to be appropriate for these papers as due to its good spatial resolution and localizing the brain activated regions. In this paper, our objective is to identify the different cognitive brain states. For example, classifying the patterns of high and low cognitive loads. We acquired the fMRI data on the healthy participants. First, data is preprocessed to remove the artifacts and motions corrections. Next, regions of interest were extracted from functional brain volumes of the two states. Data reduction is also performed and data were passed to machine learning classifier i.e., support vector machine. The results showed that high and low cognitive loads were successfully classified with good accuracy. © 2016 IEEE.